What GPU do I need to run krea/Krea-2-Raw?
A 12.8B-parameter text-to-image model. 12.8B parameters, published in BF16. View on Hugging FaceGated
Krea-2-Raw is published by krea on Hugging Face, with 75,613 downloads and 578 likes to date. It's a unlisted-architecture model built for text-to-image, published natively in BF16, and gated: you'll need to accept the model's terms on Hugging Face before downloading weights.
What Krea-2-Raw is
Krea-2-Raw is a 12.8B-parameter text-to-image model published by Krea AI on Hugging Face, released under Custom license.
License note: a lab-specific license (tagged "other" on Hugging Face); read the model card's own license section before commercial use. Facts in this section are sourced from Krea-2-Raw's Hugging Face model card, not benchmarked by Aquanode.
What it's used for
- Text-to-image generation
- Creative asset generation
- ComfyUI workflows
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for activation memory and allocator fragmentation. Diffusion and video models carry no KV-cache. The real driver of extra memory is output resolution and frame count, which this flat overhead does not model. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 23.9 GB | 28.7 GB | RTX 4080 Super | 1 | $0.338/hr |
| cheaper alt. | RTX 5060 Ti | 2 | $0.220/hr | ||
| FP8 (quantized) | 11.9 GB | 14.3 GB | RTX 5060 Ti | 1 | $0.110/hr |
| INT4 (quantized) | 6.0 GB | 7.2 GB | RTX 5060 Ti | 1 | $0.110/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Krea-2-Raw at its published (BF16) precision: 1× RTX 4080 Super, at $0.338/hr per GPU ($0.338/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Krea-2-Raw: common questions
Does Krea-2-Raw fit on a 32 GB GPU?
Yes. At BF16 it needs 28.7 GB of VRAM, so a 32 GB card holds it with 3.3 GB to spare. A 24 GB card is not enough for it at BF16.
Do I need approval to download Krea-2-Raw?
Yes. krea gates this repository on Hugging Face, so you have to accept its terms with a signed-in account before the weights will download. It does not change the 28.7 GB the model needs once you have them.
What is the least VRAM Krea-2-Raw can run in?
7.2 GB, at INT4 (quantized), which fits an 8 GB card, against 28.7 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing Krea-2-Raw lower the GPU bill?
Yes. At BF16 the cheapest live fit is one RTX 4080 Super at $0.338/hr. At FP8 (quantized) it drops to one RTX 5060 Ti at $0.110/hr, provided a quantized checkpoint exists for it.
How to run Krea-2-Raw
Run Krea-2-Raw with Diffusers (Python)
Generic example using Hugging Face's diffusers library, not from the model's own docs.
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Raw", torch_dtype=torch.bfloat16)
pipe.to("cuda")
image = pipe("a description of the scene").images[0]
image.save("output.png")Run Krea-2-Raw with ComfyUI
Aquanode's ComfyUI template comes with ComfyUI preinstalled. Download krea/Krea-2-Raw's checkpoint into the models folder and load it in a workflow; this is a real Aquanode template, but loading this specific checkpoint is a manual step, not a one-click deploy.
Deploy Krea-2-Raw on Aquanode
Aquanode has no one-click deploy template for Krea-2-Raw; it comes with ComfyUI preinstalled, so you only need to load the checkpoint, not install anything. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch the ComfyUI template sized to the requirement above (1× RTX 4080 Super or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch the ComfyUI templateWeight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More krea models
- Krea-2-Turbo (12.8B, BF16)
Related reading: H100 pricing and specs, The best GPUs for AI, ranked, and Best GPU for LLM inference.
